Description

The binary feature descriptors such as binary robust independent elementary features (BRIEF), Oriented rotated binary robust independent elementary features (ORB), and fast retin a key point (FREAK) usually perform binarisation on the intensity comparisons, thus they lose some useful information. In this study, the authors propose an effective bi nary i mage descriptor which is called significant bi t-planes based local binary pattern for visual recognition. First, the authors divide an image into several sub regions according t o t he in ten s i t y orders to incorporate the spatial information . Then the authors extract the higher bit planes for all the sub region s an d sort the adjacent neighbour bits based o n t he corresponding intensity orders, which make the descriptor invariant to rotation. In order to further improve the discriminative ability , the authors sample the multi-s ca le neighbours and average the adjacent pixels and extract the feature descript or from the higher bit planes. Since the author s directly perform operation on the significant bit p lanes without quantisation, the authors decrease the information loss To some extent. The descriptor has demonstrated a better performance over the state-of-the-art binary descriptors as well as scale invariant feature transform on two recognition benchmarks (i.e. Kentucky and ETHZ) and PASCAL 2007 for image classification.